Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbers representing the amount of casualties in violent incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to casualty figures from violent events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disclaimer
    -0.83
    flush
    -0.75
    inventoryQuantity
    -0.75
    produced
    -0.71
     evolves
    -0.70
    soType
    -0.68
    soDeliveryDate
    -0.68
     Transactions
    -0.66
    CHO
    -0.65
    given
    -0.65
    POSITIVE LOGITS
     innocent
    0.97
     bystanders
    0.93
     civilians
    0.91
     unarmed
    0.87
     pedestrians
    0.82
     occupants
    0.78
     victims
    0.78
     fleeing
    0.78
     protestors
    0.75
     innoc
    0.73
    Act Density 0.178%

    No Known Activations